Yihua Zhang


Room 3210

428 S Shaw LN

East Lansing, Michigan

United States of America

I am Yihua Zhang (张逸骅), a third-year Ph.D. student from OPTML Group at Michigan State University, supervised by Prof. Sijia Liu. My research focuses on the trustworthy and scalable ML algorithms. In general, my research spans the areas of machine learning (ML)/deep learning (DL), optimization theory, computer vision, and security. These research topics provide a solid foundation for my current and future research: Making AI system responsible and efficient. My research on these two goals are intervened and can be summarized as the following two perspectives:

:heavy_check_mark: Algorithmic perspective: This line of research designs the scalable and theoretically-grounded machine learning algorithms subject to real-life constraints, including bi-level optimization, zeroth-order optimization, inviriant risk minimization, etc.

:heavy_check_mark: Application perspective: This line of research tackles the domain-specific challenges to achieve scalable and trustworthy AI, including data and model pruning, efficient model structures, model robustness and unlearning, etc.


Jul 1, 2024 :tada: One paper accepted by ECCV’24!
May 15, 2024 :tada: Grateful to be selected as the 2024 ML and Systems Rising Star, and I will be attending the award ceremony to be held in the NVIDIA HQ in Santa Clara, CA on July 15-16!
May 1, 2024 :tada: Our ZO-Bench paper accepted in ICML 2024, check out our paper and code here!
Feb 18, 2024 :tada: Our latest dataset and benchmark on the unlearning methods for diffusion models has been released on arXiv! Check out the website, video, dataset, and benchmark!
Feb 14, 2024 :tada: Our latest benchmark on the zeroth-order optimization methods for LLM fine-tuning has been released on arXiv. Codes are also available!

First-Authored Publications

See a full publication list at here.

  1. preprint
    UnlearnCanvas: A Stylized Image Dataset to Benchmark Machine Unlearning for Diffusion Models
    Yihua Zhang, Yimeng Zhang, Yuguang Yao, Jinghan Jia, Jiancheng Liu, Xiaoming Liu, and Sijia Liu
    In arXiv preprint arXiv:2402.11846 Feb 2024
  2. ICML’24
    Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark
    Yihua Zhang, Pingzhi Li, Junyuan Hong, Jiaxiang Li, Yimeng Zhang, Wenqing Zheng, Pin-Yu Chen, Jason D. Lee, Wotao Yin, Mingyi Hong, and 3 more authors
    In arXiv preprint arXiv:2402.11592 Feb 2024
    An Introduction to Bi-level Optimization: Foundations and Applications in Signal Processing and Machine Learning
    Yihua Zhang, Prashant Khanduri, Ioannis Tsaknakis, Yuguang Yao, Mingyi Hong, and Sijia Liu
    In arxiv 2308.00788 Aug 2023
  4. NeurIPS’23
    Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning
    Yihua Zhang, Yimeng Zhang, Aochuan Chen, Jinghan Jia, Jiancheng Liu, Gaowen Liu, Mingyi Hong, Shiyu Chang, and Sijia Liu
    In Thirty-seventh Conference on Neural Information Processing Systems Aug 2023
  5. ICCV’23
    Robust Mixture-of-Expert Training for Convolutional Neural Networks
    Yihua Zhang, Ruisi Cai, Tianlong Chen, Guanhua Zhang, Huan Zhang, Pin-Yu Chen, Shiyu Chang, Zhangyang Wang, and Sijia Liu
    In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Oct 2023
  6. ICLR’23
    What Is Missing in IRM Training and Evaluation? Challenges and Solutions
    Yihua Zhang, Pranay Sharma, Parikshit Ram, Mingyi Hong, Kush Varshney, and Sijia Liu
    In Eleventh International Conference on Learning Representations Oct 2023
  7. NeurIPS’22
    Advancing Model Pruning via Bi-level Optimization
    Yihua Zhang*, Yuguang Yao*, Parikshit Ram, Pu Zhao, Tianlong Chen, Mingyi Hong, Yanzhi Wang, and Sijia Liu
    In Thirty-sixth Conference on Neural Information Processing Systems Oct 2022
  8. NeurIPS’22
    Fairness Reprogramming
    Guanhua Zhang*, Yihua Zhang*, Yang Zhang, Wenqi Fan, Qing Li, Sijia Liu, and Shiyu Chang
    In Thirty-sixth Conference on Neural Information Processing Systems Oct 2022
  9. ICML’22
    Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization
    Yihua Zhang*, Guanhua Zhang*, Prashant Khanduri, Mingyi Hong, Shiyu Chang, and Sijia Liu
    In Proceedings of the 39th International Conference on Machine Learning Oct 2022
  10. CVPR’22
    Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free
    Tianlong Chen*, Zhenyu Zhang*, Yihua Zhang*, Shiyu Chang, Sijia Liu, and Zhangyang Wang
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Oct 2022